Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/mralaminahamed/wp-dev-skills/wp-dev-learngit clone --depth 1 https://github.com/mralaminahamed/wp-dev-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/mralaminahamed/wp-dev-skills/wp-dev-learn)<a href="https://agentmods.dev/commands/mralaminahamed/wp-dev-skills/wp-dev-learn"><img src="https://agentmods.dev/badge/commands/mralaminahamed/wp-dev-skills/wp-dev-learn.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00065 | $0.02939 |
| Opus 5 | $0.00032 | $0.01470 |
| Sonnet 5 | $0.00013 | $0.00588 |
| Haiku 4.5 | $0.00006 | $0.00294 |
Grade B, and why
wp-dev-learn scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find ~/.claude/plugins/cache/wordpress-official-agent-skills -name "SKILL.md" | xargs grep -li "<topic>" How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WP Dev Skills — Learn from Session
Scan the current conversation for corrections, new rules, and edge cases, then open a PR against mralaminahamed/wp-dev-skills for each skill updated. All changes go through PR — no direct commits, owner or not.
Action: $ARGUMENTS (defaults to apply)
| Mode | Behaviour |
|---|---|
apply |
Scan → filter global-only → show table → confirm → branch-per-skill → PR per skill → assign owner |
preview |
Show what would be proposed (filtered table + candidates), no branches/PRs |
suggest |
Skip session scan — show only global WP dev topic gaps not covered by any skill |
skill:<name> |
Scope scan and PRs to one skill only; still show candidates |
Acceptance criteria — global standards only
This plugin ships rules that apply to ALL WordPress developers across ALL projects.
Rule 0 — never duplicate wordpress-official-agent-skills
Before proposing any skill update or new skill, check whether wordpress-official-agent-skills already covers the topic:
find ~/.claude/plugins/cache/wordpress-official-agent-skills -name "SKILL.md" | xargs grep -li "<topic>"
| Test | Accept | Reject |
|---|---|---|
Already fully covered by wordpress-official-agent-skills? |
❌ Reject | — |
| Partially covered — this fills a documented gap? | ✅ Accept (document boundary) | — |
| Not covered at all by official skills? | ✅ Accept | — |
If rejected by Rule 0: note it as "covered by official skills" and suggest referencing wordpress-official-agent-skills:<skill-name> instead. wp-dev-skills complements official skills — it never replicates them.
Rule 1 — global WP developer standard
Before proposing any learning, apply this filter:
| Test | Accept | Reject |
|---|---|---|
| Would a WP developer on a completely different project benefit from this rule? | ✅ Accept | ❌ Reject |
| Is the rule about a WP core API, standard tool, or universal workflow? | ✅ Accept | ❌ Reject |
| Does it reference a specific team, repo, project name, or internal tool? | ❌ Reject | — |
| Is it a QA process specific to one org's workflow? | ❌ Reject | — |
| Is it a code style preference that doesn't reflect WP/WPCS standards? | ❌ Reject | — |
| Does it assume a specific plugin architecture that isn't universal? | ❌ Reject | — |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 302 lines · 65 tokens per session scan B 97acae71f2ab
wp-dev-learn is a command published in the GitHub repository mralaminahamed/wp-dev-skills (27 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 2,939 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
init
Initialize configurations for Supabase local development.
stop
Stops the Supabase local development stack.
publish
Command "publish" from Automattic/pressship, covering publish and options.
info
pressship info pressship info ./my-plugin pressship info 16deza-table-cell-extras pressship info https://wordpress.org/plugins/16deza-table-cell-extras/ pressship info --remote pressship info ./my-plugin --remote pressship info 16deza-table-cell-extras --json.
verify
Command "verify" from Automattic/pressship, covering verify and options.
oss
Daily OSS contribution check - uses CLI with --json for structured data.